introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_83_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_80_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_8_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_79_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_78_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_77_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_75_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_76_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_74_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_73_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_72_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_71_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_70_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_69_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_68_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_7_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_67_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_66_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_65_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_64_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_63_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_61_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_60_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_62_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_12_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_6_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_59_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_0_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_11_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_58_2_epoch Updated Jan 16